You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/db/external_sst_file_ingestion...

202 lines
7.5 KiB

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
#pragma once
#include <string>
#include <unordered_set>
#include <vector>
#include "db/column_family.h"
#include "db/internal_stats.h"
#include "db/snapshot_impl.h"
#include "env/file_system_tracer.h"
#include "logging/event_logger.h"
#include "options/db_options.h"
#include "rocksdb/db.h"
#include "rocksdb/file_system.h"
#include "rocksdb/sst_file_writer.h"
#include "util/autovector.h"
namespace ROCKSDB_NAMESPACE {
class Directories;
class SystemClock;
struct IngestedFileInfo {
// External file path
std::string external_file_path;
// Smallest internal key in external file
InternalKey smallest_internal_key;
// Largest internal key in external file
InternalKey largest_internal_key;
// Sequence number for keys in external file
SequenceNumber original_seqno;
// Offset of the global sequence number field in the file, will
// be zero if version is 1 (global seqno is not supported)
size_t global_seqno_offset;
// External file size
uint64_t file_size;
// total number of keys in external file
uint64_t num_entries;
// total number of range deletions in external file
uint64_t num_range_deletions;
// Id of column family this file shoule be ingested into
uint32_t cf_id;
// TableProperties read from external file
TableProperties table_properties;
// Version of external file
int version;
// FileDescriptor for the file inside the DB
FileDescriptor fd;
// file path that we picked for file inside the DB
std::string internal_file_path;
// Global sequence number that we picked for the file inside the DB
SequenceNumber assigned_seqno = 0;
// Level inside the DB we picked for the external file.
int picked_level = 0;
// Whether to copy or link the external sst file. copy_file will be set to
// false if ingestion_options.move_files is true and underlying FS
// supports link operation. Need to provide a default value to make the
// undefined-behavior sanity check of llvm happy. Since
// ingestion_options.move_files is false by default, thus copy_file is true
// by default.
bool copy_file = true;
Ingest SST files with checksum information (#6891) Summary: Application can ingest SST files with file checksum information, such that during ingestion, DB is able to check data integrity and identify of the SST file. The PR introduces generate_and_verify_file_checksum to IngestExternalFileOption to control if the ingested checksum information should be verified with the generated checksum. 1. If generate_and_verify_file_checksum options is *FALSE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enables the SST file checksum and the checksum function name matches the checksum function name in DB, we trust the ingested checksum, store it in Manifest. If the checksum function name does not match, we treat that as an error and fail the IngestExternalFile() call. 2. If generate_and_verify_file_checksum options is *TRUE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enable the SST file checksum, we will use the checksum generator from DB to calculate the checksum for each ingested SST files after they are copied or moved. Then, compare the checksum results with the ingested checksum information: _A)_ if the checksum function name does not match, _verification always report true_ and we store the DB generated checksum information in Manifest. _B)_ if the checksum function name mach, and checksum match, ingestion continues and stores the checksum information in the Manifest. Otherwise, terminate file ingestion and report file corruption. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6891 Test Plan: added unit test, pass make asan_check Reviewed By: pdillinger Differential Revision: D21935988 Pulled By: zhichao-cao fbshipit-source-id: 7b55f486632db467e76d72602218d0658aa7f6ed
4 years ago
// The checksum of ingested file
std::string file_checksum;
// The name of checksum function that generate the checksum
std::string file_checksum_func_name;
// The temperature of the file to be ingested
Temperature file_temperature = Temperature::kUnknown;
// Unique id of the file to be ingested
UniqueId64x2 unique_id{};
};
class ExternalSstFileIngestionJob {
public:
ExternalSstFileIngestionJob(
VersionSet* versions, ColumnFamilyData* cfd,
const ImmutableDBOptions& db_options, const EnvOptions& env_options,
SnapshotList* db_snapshots,
const IngestExternalFileOptions& ingestion_options,
Directories* directories, EventLogger* event_logger,
const std::shared_ptr<IOTracer>& io_tracer)
: clock_(db_options.clock),
fs_(db_options.fs, io_tracer),
versions_(versions),
cfd_(cfd),
db_options_(db_options),
env_options_(env_options),
db_snapshots_(db_snapshots),
ingestion_options_(ingestion_options),
directories_(directories),
event_logger_(event_logger),
job_start_time_(clock_->NowMicros()),
consumed_seqno_count_(0),
io_tracer_(io_tracer) {
assert(directories != nullptr);
}
// Prepare the job by copying external files into the DB.
Status Prepare(const std::vector<std::string>& external_files_paths,
Ingest SST files with checksum information (#6891) Summary: Application can ingest SST files with file checksum information, such that during ingestion, DB is able to check data integrity and identify of the SST file. The PR introduces generate_and_verify_file_checksum to IngestExternalFileOption to control if the ingested checksum information should be verified with the generated checksum. 1. If generate_and_verify_file_checksum options is *FALSE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enables the SST file checksum and the checksum function name matches the checksum function name in DB, we trust the ingested checksum, store it in Manifest. If the checksum function name does not match, we treat that as an error and fail the IngestExternalFile() call. 2. If generate_and_verify_file_checksum options is *TRUE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enable the SST file checksum, we will use the checksum generator from DB to calculate the checksum for each ingested SST files after they are copied or moved. Then, compare the checksum results with the ingested checksum information: _A)_ if the checksum function name does not match, _verification always report true_ and we store the DB generated checksum information in Manifest. _B)_ if the checksum function name mach, and checksum match, ingestion continues and stores the checksum information in the Manifest. Otherwise, terminate file ingestion and report file corruption. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6891 Test Plan: added unit test, pass make asan_check Reviewed By: pdillinger Differential Revision: D21935988 Pulled By: zhichao-cao fbshipit-source-id: 7b55f486632db467e76d72602218d0658aa7f6ed
4 years ago
const std::vector<std::string>& files_checksums,
const std::vector<std::string>& files_checksum_func_names,
const Temperature& file_temperature, uint64_t next_file_number,
SuperVersion* sv);
// Check if we need to flush the memtable before running the ingestion job
// This will be true if the files we are ingesting are overlapping with any
// key range in the memtable.
//
// @param super_version A referenced SuperVersion that will be held for the
// duration of this function.
//
// Thread-safe
Status NeedsFlush(bool* flush_needed, SuperVersion* super_version);
// Will execute the ingestion job and prepare edit() to be applied.
// REQUIRES: Mutex held
Status Run();
// Update column family stats.
// REQUIRES: Mutex held
void UpdateStats();
// Cleanup after successful/failed job
void Cleanup(const Status& status);
VersionEdit* edit() { return &edit_; }
const autovector<IngestedFileInfo>& files_to_ingest() const {
return files_to_ingest_;
}
// How many sequence numbers did we consume as part of the ingest job?
int ConsumedSequenceNumbersCount() const { return consumed_seqno_count_; }
private:
// Open the external file and populate `file_to_ingest` with all the
// external information we need to ingest this file.
Status GetIngestedFileInfo(const std::string& external_file,
New stable, fixed-length cache keys (#9126) Summary: This change standardizes on a new 16-byte cache key format for block cache (incl compressed and secondary) and persistent cache (but not table cache and row cache). The goal is a really fast cache key with practically ideal stability and uniqueness properties without external dependencies (e.g. from FileSystem). A fixed key size of 16 bytes should enable future optimizations to the concurrent hash table for block cache, which is a heavy CPU user / bottleneck, but there appears to be measurable performance improvement even with no changes to LRUCache. This change replaces a lot of disjointed and ugly code handling cache keys with calls to a simple, clean new internal API (cache_key.h). (Preserving the old cache key logic under an option would be very ugly and likely negate the performance gain of the new approach. Complete replacement carries some inherent risk, but I think that's acceptable with sufficient analysis and testing.) The scheme for encoding new cache keys is complicated but explained in cache_key.cc. Also: EndianSwapValue is moved to math.h to be next to other bit operations. (Explains some new include "math.h".) ReverseBits operation added and unit tests added to hash_test for both. Fixes https://github.com/facebook/rocksdb/issues/7405 (presuming a root cause) Pull Request resolved: https://github.com/facebook/rocksdb/pull/9126 Test Plan: ### Basic correctness Several tests needed updates to work with the new functionality, mostly because we are no longer relying on filesystem for stable cache keys so table builders & readers need more context info to agree on cache keys. This functionality is so core, a huge number of existing tests exercise the cache key functionality. ### Performance Create db with `TEST_TMPDIR=/dev/shm ./db_bench -bloom_bits=10 -benchmarks=fillrandom -num=3000000 -partition_index_and_filters` And test performance with `TEST_TMPDIR=/dev/shm ./db_bench -readonly -use_existing_db -bloom_bits=10 -benchmarks=readrandom -num=3000000 -duration=30 -cache_index_and_filter_blocks -cache_size=250000 -threads=4` using DEBUG_LEVEL=0 and simultaneous before & after runs. Before ops/sec, avg over 100 runs: 121924 After ops/sec, avg over 100 runs: 125385 (+2.8%) ### Collision probability I have built a tool, ./cache_bench -stress_cache_key to broadly simulate host-wide cache activity over many months, by making some pessimistic simplifying assumptions: * Every generated file has a cache entry for every byte offset in the file (contiguous range of cache keys) * All of every file is cached for its entire lifetime We use a simple table with skewed address assignment and replacement on address collision to simulate files coming & going, with quite a variance (super-Poisson) in ages. Some output with `./cache_bench -stress_cache_key -sck_keep_bits=40`: ``` Total cache or DBs size: 32TiB Writing 925.926 MiB/s or 76.2939TiB/day Multiply by 9.22337e+18 to correct for simulation losses (but still assume whole file cached) ``` These come from default settings of 2.5M files per day of 32 MB each, and `-sck_keep_bits=40` means that to represent a single file, we are only keeping 40 bits of the 128-bit cache key. With file size of 2\*\*25 contiguous keys (pessimistic), our simulation is about 2\*\*(128-40-25) or about 9 billion billion times more prone to collision than reality. More default assumptions, relatively pessimistic: * 100 DBs in same process (doesn't matter much) * Re-open DB in same process (new session ID related to old session ID) on average every 100 files generated * Restart process (all new session IDs unrelated to old) 24 times per day After enough data, we get a result at the end: ``` (keep 40 bits) 17 collisions after 2 x 90 days, est 10.5882 days between (9.76592e+19 corrected) ``` If we believe the (pessimistic) simulation and the mathematical generalization, we would need to run a billion machines all for 97 billion days to expect a cache key collision. To help verify that our generalization ("corrected") is robust, we can make our simulation more precise with `-sck_keep_bits=41` and `42`, which takes more running time to get enough data: ``` (keep 41 bits) 16 collisions after 4 x 90 days, est 22.5 days between (1.03763e+20 corrected) (keep 42 bits) 19 collisions after 10 x 90 days, est 47.3684 days between (1.09224e+20 corrected) ``` The generalized prediction still holds. With the `-sck_randomize` option, we can see that we are beating "random" cache keys (except offsets still non-randomized) by a modest amount (roughly 20x less collision prone than random), which should make us reasonably comfortable even in "degenerate" cases: ``` 197 collisions after 1 x 90 days, est 0.456853 days between (4.21372e+18 corrected) ``` I've run other tests to validate other conditions behave as expected, never behaving "worse than random" unless we start chopping off structured data. Reviewed By: zhichao-cao Differential Revision: D33171746 Pulled By: pdillinger fbshipit-source-id: f16a57e369ed37be5e7e33525ace848d0537c88f
3 years ago
uint64_t new_file_number,
IngestedFileInfo* file_to_ingest,
SuperVersion* sv);
// Assign `file_to_ingest` the appropriate sequence number and the lowest
// possible level that it can be ingested to according to compaction_style.
// REQUIRES: Mutex held
Status AssignLevelAndSeqnoForIngestedFile(SuperVersion* sv,
bool force_global_seqno,
CompactionStyle compaction_style,
SequenceNumber last_seqno,
IngestedFileInfo* file_to_ingest,
SequenceNumber* assigned_seqno);
// File that we want to ingest behind always goes to the lowest level;
// we just check that it fits in the level, that DB allows ingest_behind,
// and that we don't have 0 seqnums at the upper levels.
// REQUIRES: Mutex held
Status CheckLevelForIngestedBehindFile(IngestedFileInfo* file_to_ingest);
// Set the file global sequence number to `seqno`
Status AssignGlobalSeqnoForIngestedFile(IngestedFileInfo* file_to_ingest,
SequenceNumber seqno);
Ingest SST files with checksum information (#6891) Summary: Application can ingest SST files with file checksum information, such that during ingestion, DB is able to check data integrity and identify of the SST file. The PR introduces generate_and_verify_file_checksum to IngestExternalFileOption to control if the ingested checksum information should be verified with the generated checksum. 1. If generate_and_verify_file_checksum options is *FALSE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enables the SST file checksum and the checksum function name matches the checksum function name in DB, we trust the ingested checksum, store it in Manifest. If the checksum function name does not match, we treat that as an error and fail the IngestExternalFile() call. 2. If generate_and_verify_file_checksum options is *TRUE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enable the SST file checksum, we will use the checksum generator from DB to calculate the checksum for each ingested SST files after they are copied or moved. Then, compare the checksum results with the ingested checksum information: _A)_ if the checksum function name does not match, _verification always report true_ and we store the DB generated checksum information in Manifest. _B)_ if the checksum function name mach, and checksum match, ingestion continues and stores the checksum information in the Manifest. Otherwise, terminate file ingestion and report file corruption. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6891 Test Plan: added unit test, pass make asan_check Reviewed By: pdillinger Differential Revision: D21935988 Pulled By: zhichao-cao fbshipit-source-id: 7b55f486632db467e76d72602218d0658aa7f6ed
4 years ago
// Generate the file checksum and store in the IngestedFileInfo
IOStatus GenerateChecksumForIngestedFile(IngestedFileInfo* file_to_ingest);
// Check if `file_to_ingest` can fit in level `level`
// REQUIRES: Mutex held
bool IngestedFileFitInLevel(const IngestedFileInfo* file_to_ingest,
int level);
// Helper method to sync given file.
template <typename TWritableFile>
Status SyncIngestedFile(TWritableFile* file);
SystemClock* clock_;
FileSystemPtr fs_;
VersionSet* versions_;
ColumnFamilyData* cfd_;
const ImmutableDBOptions& db_options_;
const EnvOptions& env_options_;
SnapshotList* db_snapshots_;
autovector<IngestedFileInfo> files_to_ingest_;
const IngestExternalFileOptions& ingestion_options_;
Directories* directories_;
EventLogger* event_logger_;
VersionEdit edit_;
uint64_t job_start_time_;
int consumed_seqno_count_;
// Set in ExternalSstFileIngestionJob::Prepare(), if true all files are
// ingested in L0
bool files_overlap_{false};
Ingest SST files with checksum information (#6891) Summary: Application can ingest SST files with file checksum information, such that during ingestion, DB is able to check data integrity and identify of the SST file. The PR introduces generate_and_verify_file_checksum to IngestExternalFileOption to control if the ingested checksum information should be verified with the generated checksum. 1. If generate_and_verify_file_checksum options is *FALSE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enables the SST file checksum and the checksum function name matches the checksum function name in DB, we trust the ingested checksum, store it in Manifest. If the checksum function name does not match, we treat that as an error and fail the IngestExternalFile() call. 2. If generate_and_verify_file_checksum options is *TRUE*: *1)* if DB does not enable SST file checksum, the checksum information ingested will be ignored; *2)* if DB enable the SST file checksum, we will use the checksum generator from DB to calculate the checksum for each ingested SST files after they are copied or moved. Then, compare the checksum results with the ingested checksum information: _A)_ if the checksum function name does not match, _verification always report true_ and we store the DB generated checksum information in Manifest. _B)_ if the checksum function name mach, and checksum match, ingestion continues and stores the checksum information in the Manifest. Otherwise, terminate file ingestion and report file corruption. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6891 Test Plan: added unit test, pass make asan_check Reviewed By: pdillinger Differential Revision: D21935988 Pulled By: zhichao-cao fbshipit-source-id: 7b55f486632db467e76d72602218d0658aa7f6ed
4 years ago
// Set in ExternalSstFileIngestionJob::Prepare(), if true and DB
// file_checksum_gen_factory is set, DB will generate checksum each file.
bool need_generate_file_checksum_{true};
std::shared_ptr<IOTracer> io_tracer_;
};
} // namespace ROCKSDB_NAMESPACE